When Secure Isn't: Assessing the Security of Machine Learning Model Sharing

• URL: http://arxiv.org/abs/2509.06703v2
• Date: Fri, 19 Sep 2025 15:22:16 GMT
• Title: When Secure Isn't: Assessing the Security of Machine Learning Model Sharing
• Authors: Gabriele Digregorio, Marco Di Gennaro, Stefano Zanero, Stefano Longari, Michele Carminati,
• Abstract summary: We evaluate the security posture of frameworks and hubs, assess whether security-oriented mechanisms offer real protection, and survey how users perceive the security narratives surrounding model sharing.<n>Our evaluation shows that most frameworks and hubs address security risks partially at best, often by shifting responsibility to the user.<n>We debunk the misconceptions that the model-sharing problem is largely solved and that its security can be guaranteed by the file format used for sharing.
• Score: 5.493595534345332
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rise of model-sharing through frameworks and dedicated hubs makes Machine Learning significantly more accessible. Despite their benefits, these tools expose users to underexplored security risks, while security awareness remains limited among both practitioners and developers. To enable a more security-conscious culture in Machine Learning model sharing, in this paper we evaluate the security posture of frameworks and hubs, assess whether security-oriented mechanisms offer real protection, and survey how users perceive the security narratives surrounding model sharing. Our evaluation shows that most frameworks and hubs address security risks partially at best, often by shifting responsibility to the user. More concerningly, our analysis of frameworks advertising security-oriented settings and complete model sharing uncovered six 0-day vulnerabilities enabling arbitrary code execution. Through this analysis, we debunk the misconceptions that the model-sharing problem is largely solved and that its security can be guaranteed by the file format used for sharing. As expected, our survey shows that the surrounding security narrative leads users to consider security-oriented settings as trustworthy, despite the weaknesses shown in this work. From this, we derive takeaways and suggestions to strengthen the security of model-sharing ecosystems.

Related papers

• An Empirical Study on Remote Code Execution in Machine Learning Model Hosting Ecosystems [4.409447722044799]
  Execution of untrusted code during model loading is a security concern for model-sharing platforms.<n>We conduct the first large-scale empirical study of custom model loading practices across five major model-sharing platforms.
  arXiv  Detail & Related papers  (2026-01-20T17:13:42Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning [76.56522719330911]
  Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering.<n>LRMs pose great safety risks against harmful queries and adversarial attacks.<n>We propose SafeKey to better activate the safety aha moment in the key sentence.
  arXiv  Detail & Related papers  (2025-05-22T03:46:03Z)
• Towards Trustworthy GUI Agents: A Survey [64.6445117343499]
  This survey examines the trustworthiness of GUI agents in five critical dimensions.<n>We identify major challenges such as vulnerability to adversarial attacks, cascading failure modes in sequential decision-making.<n>As GUI agents become more widespread, establishing robust safety standards and responsible development practices is essential.
  arXiv  Detail & Related papers  (2025-03-30T13:26:00Z)
• AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement [73.0700818105842]
  We introduce AISafetyLab, a unified framework and toolkit that integrates representative attack, defense, and evaluation methodologies for AI safety.<n> AISafetyLab features an intuitive interface that enables developers to seamlessly apply various techniques.<n>We conduct empirical studies on Vicuna, analyzing different attack and defense strategies to provide valuable insights into their comparative effectiveness.
  arXiv  Detail & Related papers  (2025-02-24T02:11:52Z)
• Building a Cybersecurity Risk Metamodel for Improved Method and Tool Integration [0.38073142980732994]
  We report on our experience in applying a model-driven approach on the initial risk analysis step in connection with a later security testing. Our work rely on a common metamodel which is used to map, synchronise and ensure information traceability across different tools.
  arXiv  Detail & Related papers  (2024-09-12T10:18:26Z)
• Trust, but Verify: Evaluating Developer Behavior in Mitigating Security Vulnerabilities in Open-Source Software Projects [0.11999555634662631]
  This study investigates vulnerabilities in dependencies of sampled open-source software (OSS) projects. We have identified common issues in outdated or unmaintained dependencies, that pose significant security risks. Results suggest that reducing the number of direct dependencies and prioritizing well-established libraries with strong security records are effective strategies for enhancing the software security landscape.
  arXiv  Detail & Related papers  (2024-08-26T13:46:48Z)
• Securing Federated Learning with Control-Flow Attestation: A Novel Framework for Enhanced Integrity and Resilience against Adversarial Attacks [2.28438857884398]
  Federated Learning (FL) as a distributed machine learning paradigm has introduced new cybersecurity challenges. This study proposes an innovative security framework inspired by Control-Flow (CFA) mechanisms, traditionally used in cybersecurity. We authenticate and verify the integrity of model updates across the network, effectively mitigating risks associated with model poisoning and adversarial interference.
  arXiv  Detail & Related papers  (2024-03-15T04:03:34Z)
• Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements [76.80453043969209]
  This survey presents a framework for safety research pertaining to large models. We begin by introducing safety issues of wide concern, then delve into safety evaluation methods for large models. We explore the strategies for enhancing large model safety from training to deployment.
  arXiv  Detail & Related papers  (2023-02-18T09:32:55Z)
• Do Software Security Practices Yield Fewer Vulnerabilities? [6.6840472845873276]
  The goal of this study is to assist practitioners and researchers making informed decisions on which security practices to adopt. Four security practices were the most important practices influencing vulnerability count. The number of reported vulnerabilities increased rather than reduced as the aggregate security score of the packages increased.
  arXiv  Detail & Related papers  (2022-10-20T20:04:02Z)
• Risk Management Framework for Machine Learning Security [7.678455181587705]
  Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. In this paper, we outline a novel framework to guide the risk management process for organizations reliant on machine learning models.
  arXiv  Detail & Related papers  (2020-12-09T06:21:34Z)
• Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
  Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance. We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
  arXiv  Detail & Related papers  (2020-10-19T13:09:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.